I’m a PhD student advised by Prof. Chaoyue Liu, researching aspects of optimization theory, intrinsic interpretability, & domain generalization.

I aim to develop methods for leveraging intuitive biases which enable learning parameters that produce emergent behaviors while remaining interpretable by design.

Besides Machine Learning, I enjoy hiking, motor racing, chess, swimming, mountain biking (although I currently suck at this one) & anything that gets my adrenaline pumping.

If you’re working on something interesting / want to chat about some technical challenge within interpretability / optimization theory, free to set up a time for us to chat via this scheduler!